Update config.py

config.py

@@ -1,21 +1,20 @@
 import os
 
-# --- Paths ---
+# === Base Directory ===
 BASE_DIR = os.path.abspath(os.path.dirname(__file__))
 
-# Path to dataset
+# === Dataset Path ===
 DATA_PATH = os.path.join(BASE_DIR, "data", "synthetic_transactions_samples_5000.csv")
 
-# Directory to save models
+# === Model Save Paths ===
 MODEL_SAVE_DIR = os.path.join(BASE_DIR, "models")
 os.makedirs(MODEL_SAVE_DIR, exist_ok=True)
 
-# Save paths for Logistic Regression model + artifacts
-MODEL_PATH = os.path.join(MODEL_SAVE_DIR, "logreg_model.pkl")              # ✅ Logistic Regression model
+MODEL_PATH = os.path.join(MODEL_SAVE_DIR, "logreg_model.pkl")
 TFIDF_VECTORIZER_PATH = os.path.join(MODEL_SAVE_DIR, "tfidf_vectorizer.pkl")
 LABEL_ENCODERS_PATH = os.path.join(MODEL_SAVE_DIR, "label_encoders.pkl")
 
-# --- Text & Label Columns ---
+# === Columns ===
 TEXT_COLUMN = "Sanction_Context"
 LABEL_COLUMNS = [
     "Red_Flag_Reason",
@@ -26,11 +25,11 @@ LABEL_COLUMNS = [
     "Investigation_Outcome"
 ]
 
-# --- TF-IDF Settings ---
+# === TF-IDF Settings ===
 TFIDF_MAX_FEATURES = 5000
 NGRAM_RANGE = (1, 2)
-USE_STOPWORDS = True  # English stopwords will be removed if True
+USE_STOPWORDS = True
 
-# --- Train/Test Split ---
-RANDOM_STATE = 42
+# === Train/Test Split Settings ===
 TEST_SIZE = 0.2
+RANDOM_STATE = 42